© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211310
    Prev
    Next
    INDEX
    Explanations

    -assa endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ون
    1.56
    ام
    1.36
    ana
    1.34
    em
    1.33
    ?
    1.27
    !
    1.27
    ed
    1.23
    s
    1.23
    ot
    1.20
    i
    1.20
    POSITIVE LOGITS
    ë
    1.24
    к
    1.10
    ﺼ
    1.10
    ມັນ
    1.09
    ް
    1.09
    the
    1.07
    یر
    1.04
    ﺮ
    1.03
    ルの
    1.02
    ﺘ
    1.00
    Activations Density 0.000%

    No Known Activations